lib/Unicode/UCD.t

   1 use Unicode::UCD;
   2
   3 use strict;
   4
   5 BEGIN {
   6     if (ord("A") == 193) {
   7         print "1..0 # Skip: EBCDIC\n";
   8         exit 0;
   9     }
  10 }
  11
  12 use Test;
  13
  14 BEGIN { plan tests => 162 };
  15
  16 use Unicode::UCD 'charinfo';
  17
  18 my $charinfo;
  19
  20 $charinfo = charinfo(0x41);
  21
  22 ok($charinfo->{code},           '0041');
  23 ok($charinfo->{name},           'LATIN CAPITAL LETTER A');
  24 ok($charinfo->{category},       'Lu');
  25 ok($charinfo->{combining},      '0');
  26 ok($charinfo->{bidi},           'L');
  27 ok($charinfo->{decomposition},  '');
  28 ok($charinfo->{decimal},        '');
  29 ok($charinfo->{digit},          '');
  30 ok($charinfo->{numeric},        '');
  31 ok($charinfo->{mirrored},       'N');
  32 ok($charinfo->{unicode10},      '');
  33 ok($charinfo->{comment},        '');
  34 ok($charinfo->{upper},          '');
  35 ok($charinfo->{lower},          '0061');
  36 ok($charinfo->{title},          '');
  37 ok($charinfo->{block},          'Basic Latin');
  38 ok($charinfo->{script},         'Latin');
  39
  40 $charinfo = charinfo(0x100);
  41
  42 ok($charinfo->{code},           '0100');
  43 ok($charinfo->{name},           'LATIN CAPITAL LETTER A WITH MACRON');
  44 ok($charinfo->{category},       'Lu');
  45 ok($charinfo->{combining},      '0');
  46 ok($charinfo->{bidi},           'L');
  47 ok($charinfo->{decomposition},  '0041 0304');
  48 ok($charinfo->{decimal},        '');
  49 ok($charinfo->{digit},          '');
  50 ok($charinfo->{numeric},        '');
  51 ok($charinfo->{mirrored},       'N');
  52 ok($charinfo->{unicode10},      'LATIN CAPITAL LETTER A MACRON');
  53 ok($charinfo->{comment},        '');
  54 ok($charinfo->{upper},          '');
  55 ok($charinfo->{lower},          '0101');
  56 ok($charinfo->{title},          '');
  57 ok($charinfo->{block},          'Latin Extended-A');
  58 ok($charinfo->{script},         'Latin');
  59
  60 # 0x0590 is in the Hebrew block but unused.
  61
  62 $charinfo = charinfo(0x590);
  63
  64 ok($charinfo->{code},          undef);
  65 ok($charinfo->{name},          undef);
  66 ok($charinfo->{category},      undef);
  67 ok($charinfo->{combining},     undef);
  68 ok($charinfo->{bidi},          undef);
  69 ok($charinfo->{decomposition}, undef);
  70 ok($charinfo->{decimal},       undef);
  71 ok($charinfo->{digit},         undef);
  72 ok($charinfo->{numeric},       undef);
  73 ok($charinfo->{mirrored},      undef);
  74 ok($charinfo->{unicode10},     undef);
  75 ok($charinfo->{comment},       undef);
  76 ok($charinfo->{upper},         undef);
  77 ok($charinfo->{lower},         undef);
  78 ok($charinfo->{title},         undef);
  79 ok($charinfo->{block},         undef);
  80 ok($charinfo->{script},        undef);
  81
  82 # 0x05d0 is in the Hebrew block and used.
  83
  84 $charinfo = charinfo(0x5d0);
  85
  86 ok($charinfo->{code},           '05D0');
  87 ok($charinfo->{name},           'HEBREW LETTER ALEF');
  88 ok($charinfo->{category},       'Lo');
  89 ok($charinfo->{combining},      '0');
  90 ok($charinfo->{bidi},           'R');
  91 ok($charinfo->{decomposition},  '');
  92 ok($charinfo->{decimal},        '');
  93 ok($charinfo->{digit},          '');
  94 ok($charinfo->{numeric},        '');
  95 ok($charinfo->{mirrored},       'N');
  96 ok($charinfo->{unicode10},      '');
  97 ok($charinfo->{comment},        '');
  98 ok($charinfo->{upper},          '');
  99 ok($charinfo->{lower},          '');
 100 ok($charinfo->{title},          '');
 101 ok($charinfo->{block},          'Hebrew');
 102 ok($charinfo->{script},         'Hebrew');
 103
 104 # An open syllable in Hangul.
 105
 106 $charinfo = charinfo(0xAC00);
 107
 108 ok($charinfo->{code},           'AC00');
 109 ok($charinfo->{name},           'HANGUL SYLLABLE-AC00');
 110 ok($charinfo->{category},       'Lo');
 111 ok($charinfo->{combining},      '0');
 112 ok($charinfo->{bidi},           'L');
 113 ok($charinfo->{decomposition},  undef);
 114 ok($charinfo->{decimal},        '');
 115 ok($charinfo->{digit},          '');
 116 ok($charinfo->{numeric},        '');
 117 ok($charinfo->{mirrored},       'N');
 118 ok($charinfo->{unicode10},      '');
 119 ok($charinfo->{comment},        '');
 120 ok($charinfo->{upper},          '');
 121 ok($charinfo->{lower},          '');
 122 ok($charinfo->{title},          '');
 123 ok($charinfo->{block},          'Hangul Syllables');
 124 ok($charinfo->{script},         'Hangul');
 125
 126 # A closed syllable in Hangul.
 127
 128 $charinfo = charinfo(0xAE00);
 129
 130 ok($charinfo->{code},           'AE00');
 131 ok($charinfo->{name},           'HANGUL SYLLABLE-AE00');
 132 ok($charinfo->{category},       'Lo');
 133 ok($charinfo->{combining},      '0');
 134 ok($charinfo->{bidi},           'L');
 135 ok($charinfo->{decomposition},  undef);
 136 ok($charinfo->{decimal},        '');
 137 ok($charinfo->{digit},          '');
 138 ok($charinfo->{numeric},        '');
 139 ok($charinfo->{mirrored},       'N');
 140 ok($charinfo->{unicode10},      '');
 141 ok($charinfo->{comment},        '');
 142 ok($charinfo->{upper},          '');
 143 ok($charinfo->{lower},          '');
 144 ok($charinfo->{title},          '');
 145 ok($charinfo->{block},          'Hangul Syllables');
 146 ok($charinfo->{script},         'Hangul');
 147
 148 $charinfo = charinfo(0x1D400);
 149
 150 ok($charinfo->{code},           '1D400');
 151 ok($charinfo->{name},           'MATHEMATICAL BOLD CAPITAL A');
 152 ok($charinfo->{category},       'Lu');
 153 ok($charinfo->{combining},      '0');
 154 ok($charinfo->{bidi},           'L');
 155 ok($charinfo->{decomposition},  '<font> 0041');
 156 ok($charinfo->{decimal},        '');
 157 ok($charinfo->{digit},          '');
 158 ok($charinfo->{numeric},        '');
 159 ok($charinfo->{mirrored},       'N');
 160 ok($charinfo->{unicode10},      '');
 161 ok($charinfo->{comment},        '');
 162 ok($charinfo->{upper},          '');
 163 ok($charinfo->{lower},          '');
 164 ok($charinfo->{title},          '');
 165 ok($charinfo->{block},          'Mathematical Alphanumeric Symbols');
 166 ok($charinfo->{script},         undef);
 167
 168 use Unicode::UCD qw(charblock charscript);
 169
 170 # 0x0590 is in the Hebrew block but unused.
 171
 172 ok(charblock(0x590),          'Hebrew');
 173 ok(charscript(0x590),         undef);
 174
 175 $charinfo = charinfo(0xbe);
 176
 177 ok($charinfo->{code},           '00BE');
 178 ok($charinfo->{name},           'VULGAR FRACTION THREE QUARTERS');
 179 ok($charinfo->{category},       'No');
 180 ok($charinfo->{combining},      '0');
 181 ok($charinfo->{bidi},           'ON');
 182 ok($charinfo->{decomposition},  '<fraction> 0033 2044 0034');
 183 ok($charinfo->{decimal},        '');
 184 ok($charinfo->{digit},          '');
 185 ok($charinfo->{numeric},        '3/4');
 186 ok($charinfo->{mirrored},       'N');
 187 ok($charinfo->{unicode10},      'FRACTION THREE QUARTERS');
 188 ok($charinfo->{comment},        '');
 189 ok($charinfo->{upper},          '');
 190 ok($charinfo->{lower},          '');
 191 ok($charinfo->{title},          '');
 192 ok($charinfo->{block},          'Latin-1 Supplement');
 193 ok($charinfo->{script},         undef);
 194
 195 use Unicode::UCD qw(charblocks charscripts);
 196
 197 my $charblocks = charblocks();
 198
 199 ok(exists $charblocks->{Thai});
 200 ok($charblocks->{Thai}->[0]->[0], hex('0e00'));
 201 ok(!exists $charblocks->{PigLatin});
 202
 203 my $charscripts = charscripts();
 204
 205 ok(exists $charscripts->{Armenian});
 206 ok($charscripts->{Armenian}->[0]->[0], hex('0531'));
 207 ok(!exists $charscripts->{PigLatin});
 208
 209 my $charscript;
 210
 211 $charscript = charscript("12ab");
 212 ok($charscript, 'Ethiopic');
 213
 214 $charscript = charscript("0x12ab");
 215 ok($charscript, 'Ethiopic');
 216
 217 $charscript = charscript("U+12ab");
 218 ok($charscript, 'Ethiopic');
 219
 220 my $ranges;
 221
 222 $ranges = charscript('Ogham');
 223 ok($ranges->[0]->[0], hex('1681'));
 224 ok($ranges->[0]->[1], hex('169a'));
 225
 226 use Unicode::UCD qw(charinrange);
 227
 228 $ranges = charscript('Cherokee');
 229 ok(!charinrange($ranges, "139f"));
 230 ok( charinrange($ranges, "13a0"));
 231 ok( charinrange($ranges, "13f4"));
 232 ok(!charinrange($ranges, "13f5"));
 233
 234 ok(Unicode::UCD::UnicodeVersion, '3.1.1');
 235
 236 use Unicode::UCD qw(compexcl);
 237
 238 ok(!compexcl(0x0100));
 239 ok( compexcl(0x0958));
 240
 241 use Unicode::UCD qw(casefold);
 242
 243 my $casefold;
 244
 245 $casefold = casefold(0x41);
 246
 247 ok($casefold->{code} eq '0041' &&
 248    $casefold->{status} eq 'C'  &&
 249    $casefold->{mapping} eq '0061');
 250
 251 $casefold = casefold(0xdf);
 252
 253 ok($casefold->{code} eq '00DF' &&
 254    $casefold->{status} eq 'F'  &&
 255    $casefold->{mapping} eq '0073 0073');
 256
 257 ok(!casefold(0x20));
 258
 259 use Unicode::UCD qw(casespec);
 260
 261 my $casespec;
 262
 263 ok(!casespec(0x41));
 264
 265 $casespec = casespec(0xdf);
 266
 267 ok($casespec->{code} eq '00DF' &&
 268    $casespec->{lower} eq '00DF'  &&
 269    $casespec->{title} eq '0053 0073'  &&
 270    $casespec->{upper} eq '0053 0053' &&
 271    $casespec->{condition} eq undef);
 272
 273 $casespec = casespec(0x307);
 274
 275 ok($casespec->{az}->{code} eq '0307' &&
 276    $casespec->{az}->{lower} eq ''  &&
 277    $casespec->{az}->{title} eq '0307'  &&
 278    $casespec->{az}->{upper} eq '0307' &&
 279    $casespec->{az}->{condition} eq 'az AFTER_i NOT_MORE_ABOVE');